Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mnlt/teleport/vercelnpx skills add mnlt/teleport --skill vercelgit clone --depth 1 https://github.com/mnlt/teleportWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mnlt/teleport/vercel)<a href="https://agentmods.dev/skills/mnlt/teleport/vercel"><img src="https://agentmods.dev/badge/skills/mnlt/teleport/vercel.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.01939 |
| Opus 5 | $0.00030 | $0.00970 |
| Sonnet 5 | $0.00012 | $0.00388 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade B, and why
vercel scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Do NOT suggest editing `~/.claude/settings.local.json` manually.** The `teleport-setup add-key` command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restar Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL -H "Authorization: Bearer $VERCEL_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel
Operates Vercel via REST API — deployments, projects, env vars, domains/DNS, logs, teams, webhooks, Edge Config. Prefer over vercel CLI for scripted/team-scoped control.
Usage
- Use for: Deploy status, triggering redeploys, rotating env vars, attaching domains, tailing build/runtime logs.
- Skip for: Framework/docs questions (use Context7), local build failures (
vercel dev), editingvercel.jsonin a repo.
Credentials check
[ -n "$VERCEL_TOKEN" ] && echo "VERCEL_TOKEN: PRESENT" || echo "VERCEL_TOKEN: MISSING"
Never echo the variable directly — the value would appear in the conversation transcript.
If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):
I need your vercel credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:
teleport-setup add-key vercelThen restart Claude Code (
/exit, thenclaude) and ask me again.
Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.
API
- Base URL:
https://api.vercel.com - Auth:
Authorization: Bearer $VERCEL_TOKEN teamId— #1 silent footgun. Team-scoped tokens calling an endpoint without?teamId=team_xxx(orslug=) silently fall back to personal scope — wrong/empty results with 200 OK.GET /v2/teamsonce, cache, append everywhere.- Versioning is per-endpoint in the path — list env vars is
v10, update isv9, create project isv11, update project isv9. Guessing 404s; use the table. - Pagination is timestamp-based, not an opaque token.
pagination.nextis a unix millisecond value; pass asuntil=(orsince=to walk forward). Project list usesfrom. - Rate limits per-endpoint; headers:
x-ratelimit-limit,x-ratelimit-remaining,x-ratelimit-reset(unix sec). Notable: runtime logs 100/min, env create/update 120/min, env delete 60/min, domain create 120/hr, DNS create 100/hr. - OpenAPI spec:
https://openapi.vercel.sh/(single large JSON).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 111 lines · 59 tokens per session scan B 9282a9884f26
vercel is a skill published in the GitHub repository mnlt/teleport (8 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
discovery-patterns
Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…
xfuel-route-compute
Inspect XFuel's 6-tier DePIN compute router and preview which GPU provider a task will hit (Theta EdgeCloud → RapidAPI → MCP → Akash → Render → AWS Bedrock), plus check server health and available chains/models. Use when a user asks "which provider will run this?", "is EdgeCloud available?", "what does XFuel route…
hostinger-deploy
Hostinger-specific deployment protocol handling OPcache, CDN caching, and hPanel Git mechanism. Activates for "deploy to hostinger", "hostinger", "redeploy", "publish website", "push to production" when target is Hostinger.
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.